Gunn_Compiler/lexer.cpp at main · gunnseth55/Gunn_Compiler · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
#include "lexer.h"
#include <cctype>
using namespace std;
Lexer::Lexer(const string &input): input(input), pos(0) {}
char Lexer::peek(){
    if(pos>=input.size())return '\0';
    return input[pos];
}
char Lexer::get(){
    return input[pos++];

}

vector<Token> Lexer::tokenize(){
    vector<Token>tokens;
    while(pos<input.size()){
        char c=peek();
        if(isspace(c)){
            get();
            continue;
        }
        if(isalpha(c)){
            string word;
            while(pos<input.size() && isalnum(peek())) word+=get();

            if(word =="int")tokens.push_back({INT,word});
            else if (word == "return") tokens.push_back({RETURN,word});
            else if (word == "if") tokens.push_back({IF,word});
            else if (word=="else")tokens.push_back({ELSE,word});
            else if(word=="while")tokens.push_back({WHILE,word});
            else if(word=="for")tokens.push_back({FOR,word});
            else if(word=="break")tokens.push_back({BREAK,word});
            else if(word=="continue")tokens.push_back({CONTINUE,word});
            else tokens.push_back({IDENTIFIER,word});
        }else if(isdigit(c)){
            string num;
            while(pos<input.size() && isdigit(peek())) num+=get();
            tokens.push_back({NUMBER,num});
        }else if(c=='+'){
            get();
            tokens.push_back({PLUS,"+"});
        }else if(c=='='){
            get();
            if(peek()=='='){
                get();
                tokens.push_back({EQUAL_EQUAL,"=="});
            }else{
                tokens.push_back({EQUAL,"="});
            }
        }else if(c=='-'){
            get();
            tokens.push_back({MINUS,"-"});
        }else if(c=='*'){
            get();
            tokens.push_back({MULTIPLY,"*"});
        }else if(c=='/'){
            get();
            tokens.push_back({DIVIDE,"/"});
        } else if(c==';'){
            get();
            tokens.push_back({SEMICOLON,";"});
        }else if(c=='<'){
            get();
            if(peek()=='='){
                get();
                tokens.push_back({LESS_EQUAL,"<="});
            }else{
                tokens.push_back({LESS,"<"});
            }
        }else if(c=='>'){
            get();
            if(peek()=='='){
                get();
                tokens.push_back({GREATER_EQUAL,">="});
            }else{
                tokens.push_back({GREATER,">"});
            }
        }else if(c=='('){
            get();
            tokens.push_back({LPAREN,"("});
        }else if(c==')'){
            get();
            tokens.push_back({RPAREN,")"});
        }else if(c=='{'){
            get();
            tokens.push_back({LBRACE,"{"});
        }else if(c=='}'){
            get();
            tokens.push_back({RBRACE,"}"});
        }


        else
        {
            get();
        }

    }
    tokens.push_back({END,""});
    return tokens;
}